Proceedings of the Eighteenth International Conference on Principles of Knowledge Representation and Reasoning 2021
DOI: 10.24963/kr.2021/8
|View full text |Cite
|
Sign up to set email alerts
|

On the Computational Intelligibility of Boolean Classifiers

Abstract: In this paper, we investigate the computational intelligibility of Boolean classifiers, characterized by their ability to answer XAI queries in polynomial time. The classifiers under consideration are decision trees, DNF formulae, decision lists, decision rules, tree ensembles, and Boolean neural nets. Using 9 XAI queries, including both explanation queries and verification queries, we show the existence of large intelligibility gap between the families of classifiers. On th… Show more

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2
2
1

Citation Types

1
45
0
1

Year Published

2021
2021
2024
2024

Publication Types

Select...
5
1

Relationship

0
6

Authors

Journals

citations
Cited by 28 publications
(47 citation statements)
references
References 20 publications
1
45
0
1
Order By: Relevance
“…κ : F → K. We now define formal explanations. Prime implicant (PI) explanations [36] denote a minimal set of literals (relating a feature value x i and a constant v i ∈ D i that are sufficient for the prediction 1 .…”
Section: Preliminariesmentioning
confidence: 99%
See 4 more Smart Citations
“…κ : F → K. We now define formal explanations. Prime implicant (PI) explanations [36] denote a minimal set of literals (relating a feature value x i and a constant v i ∈ D i that are sufficient for the prediction 1 .…”
Section: Preliminariesmentioning
confidence: 99%
“…1 PI-explanations are related with abduction, and so are also referred to as abductive explanations (AXp) [14]. More recently, PI-explanations have been studied from a knowledge compilation perspective [2,1], but also in terms of their computational complexity [3].…”
Section: Preliminariesmentioning
confidence: 99%
See 3 more Smart Citations